© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1814
    Prev
    Next
    INDEX
    Explanations

    Temperature and dairy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.57
    I
    0.56
     I
    0.54
    iversary
    0.54
    up
    0.51
    ters
    0.51
    raise
    0.48
    by
    0.47
    ，《
    0.47
    if
    0.46
    POSITIVE LOGITS
     новости
    0.51
     স্বাগত
    0.47
     বর্ণ
    0.46
    用
    0.45
    剖
    0.45
    ட்சய
    0.44
    邮件
    0.43
    顶部
    0.43
    曲
    0.43
    嶙
    0.43
    Activations Density 0.001%

    No Known Activations